INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

dayName

-0.74

REDACTED

-0.73

phas

-0.72

inent

-0.69

RESULTS

-0.65

 Neon

-0.65

toggle

-0.65

shit

-0.64

advertisement

-0.64

 relay

-0.62

POSITIVE LOGITS

itter

0.73

iste

0.65

abee

0.65

Db

0.64

 Aberdeen

0.64

Marginal

0.64

EMBER

0.62

ointed

0.61

Ã©e

0.61

ERY

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.